LKD读书笔记（process Scheduling）

1.  Process Selection

      When CFS is deciding what process to run next , it picks the process with the smallest vruntime. This is the core of CFS's scheduling algotithm: Pick the task with the smallest vruntime.

      CFS uses a red-black tree to manage the list of runnable processes and efficiently find the process with the smallest vruntiome.

2. Pick the Next Task

static struct sched_entyty *_pick_next_entity(struct cfs_rq *cfs_rq)
{
    struct rb_node *left = cfs_rq->rb_leftmost;
    if (!left)
        return NULL;
    return rb_entry(left, struct sched_entity, run_node);
}

3. adding processes to the tree

   这个发生在一个进程变成runnable状态或者第一次通过fork()创建

cfs_rq:  CFS-related fields in a runqueue

struct cfs_rq {
        struct load_weight load;
        unsigned long nr_running;

        u64 exec_clock;
        u64 min_vruntime;

        struct rb_root tasks_timeline;
        struct rb_node *rb_leftmost;

        struct list_head tasks;
        struct list_head *balance_iterator;

        /*
         * 'curr' points to currently running entity on this cfs_rq.
         * It is set to NULL otherwise (i.e when none are currently running).
         */
        struct sched_entity *curr, *next, *last;

        unsigned int nr_spread_over;

#ifdef CONFIG_FAIR_GROUP_SCHED
        struct rq *rq;  /* cpu runqueue to which this cfs_rq is attached */

        /*
         * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
         * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
         * (like users, containers etc.)
         *
         * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
         * list is used during load balance.
         */
        int on_list;
        struct list_head leaf_cfs_rq_list;
        struct task_group *tg;  /* group that "owns" this runqueue */

#ifdef CONFIG_SMP
        /*
         * the part of load.weight contributed by tasks
         */
        unsigned long task_weight;

        /*
         *   h_load = weight * f(tg)
         *
         * Where f(tg) is the recursive weight fraction assigned to
         * this group.
         */
        unsigned long h_load;

        /*
         * Maintaining per-cpu shares distribution for group scheduling
         *
         * load_stamp is the last time we updated the load average
         * load_last is the last time we updated the load average and saw load
         * load_unacc_exec_time is currently unaccounted execution time
         */
        u64 load_avg;
        u64 load_period;
        u64 load_stamp, load_last, load_unacc_exec_time;

        unsigned long load_contribution;
#endif
#endif
};

static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
{
        /*
         * Update the normalized vruntime before updating min_vruntime
         * through callig update_curr().
         */
        if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
                se->vruntime += cfs_rq->min_vruntime;

        /*
         * Update run-time statistics of the 'current'.
         */
        update_curr(cfs_rq);
        update_cfs_load(cfs_rq, 0);
        update_cfs_shares(cfs_rq, se->load.weight);
        account_entity_enqueue(cfs_rq, se);

        if (flags & ENQUEUE_WAKEUP) {
                place_entity(cfs_rq, se, 0);
                enqueue_sleeper(cfs_rq, se);
        }

        update_stats_enqueue(cfs_rq, se);
        check_spread(cfs_rq, se);
        if (se != cfs_rq->curr)
                __enqueue_entity(cfs_rq, se);
        se->on_rq = 1;

        if (cfs_rq->nr_running == 1)
                list_add_leaf_cfs_rq(cfs_rq);
}

/*
 * Enqueue an entity into the rb-tree:
 */
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
        struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
        struct rb_node *parent = NULL;
        struct sched_entity *entry;
        s64 key = entity_key(cfs_rq, se);
        int leftmost = 1;

        /*
         * Find the right place in the rbtree:
         */
        while (*link) {
                parent = *link;
                entry = rb_entry(parent, struct sched_entity, run_node);
                /*
                 * We dont care about collisions. Nodes with
                 * the same key stay together.
                 */
                if (key < entity_key(cfs_rq, entry)) {
                        link = &parent->rb_left;
                } else {
                        link = &parent->rb_right;
                        leftmost = 0;
                }
        }

        /*
         * Maintain a cache of leftmost tree entries (it is frequently
         * used):
         */
        if (leftmost)
                cfs_rq->rb_leftmost = &se->run_node;

        rb_link_node(&se->run_node, parent, link);
        rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}